A method, apparatus and system for induction furnace heating control

Abstract

The application relates to the technical field of induction heating temperature control, in particular to an induction furnace heating control method, equipment and system, the method comprising the following steps: acquiring an infrared thermal imaging image in an induction furnace heating process; obtaining environmental medium interference through granular noise characteristics and edge gradient characteristics in the infrared thermal imaging image of the induction furnace; obtaining induction heating sufficiency according to skin effect characteristics and temperature change trend characteristics in the infrared thermal imaging image of the induction furnace; obtaining a heating control factor according to the environmental medium interference and the induction heating sufficiency; evaluating the overall heating condition of materials in the induction furnace through the heating control factor, and adjusting the induction coil temperature of the induction furnace according to the heating control factor. The application aims to accurately adjust the induction coil temperature of the induction furnace, improve the energy transmission efficiency of the induction furnace, improve the automatic control precision and reduce the energy consumption.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of induction heating temperature control, in particular to an induction furnace heating control method, device and system. BACKGROUND

[0002] An induction furnace is an electric furnace that uses the induction electric heating effect of materials to heat or melt the materials. According to the principle of electromagnetic induction, an alternating magnetic field is generated by an induction coil, which forms eddy currents and magnetic hysteresis effects (for ferromagnetic materials) inside the heated materials, thereby converting electrical energy into heat energy. Induction furnace heating control technology adjusts the induction power supply to accurately control the heating temperature, effectively improve the heating efficiency, reduce energy waste, meet the requirements of different materials and processes for heating precision, and realize intelligent production and operation of the induction furnace.

[0003] The induction coil is the core component of the induction furnace heating. By controlling the temperature of the induction coil, the energy consumption of the induction furnace can be effectively reduced, the energy transfer efficiency can be improved, and the material heating condition can be accurately adjusted. Traditional monitoring methods such as thermocouple sensors can only obtain discrete point temperatures, but cannot capture the temperature field distortion caused by the eddy current distribution in the induction furnace. Although infrared thermal imaging technology can accurately capture the global temperature field and transient changes of the material induction heating, the medium interference in the induction furnace produces shot noise in the infrared thermal imaging image, causing temperature misjudgment of the material induction heating. At the same time, due to the skin effect of the material caused by the alternating electromagnetic field of the induction coil, the eddy current density on the surface of the material is much higher than that inside, causing the surface temperature of the material to rise faster and forming temperature distribution distortion, which affects the accurate discrimination of the temperature field formed by the induction coil. SUMMARY

[0004] In view of the above, it is necessary to provide an induction furnace heating control method, device and system to solve the above problems.

[0005] According to an aspect of the present application, an induction furnace heating control method is provided, which comprises:

[0006] obtaining infrared thermal imaging images of all frames in the induction furnace heating process;

[0007] presetting a neighborhood window of the infrared thermal imaging image, segmenting the gray value of each pixel in each neighborhood window to obtain dark spot pixels, analyzing the gray distribution difference between all dark spot pixels and remaining pixels in each neighborhood window, combining the position distribution of all dark spot pixels to obtain the shot noise condition of each neighborhood window, analyzing the distribution of the gray gradient and the distribution of the gray gradient direction angle of the edge pixels in each neighborhood window to obtain the edge gradient blur condition of each neighborhood window, and performing forward fusion on the shot noise condition and the edge gradient blur condition of each neighborhood window to obtain the environmental medium interference of each neighborhood window;

[0008] analyze the distribution characteristics of the gray value of each edge pixel in the vertical direction of each neighborhood window to obtain the skin effect severity of each neighborhood window; based on the similarity of the gray distribution of each neighborhood window and the rest of the neighborhood windows in the current frame and all previous frames of the infrared thermal imaging image, obtain the heating sufficiency of each neighborhood window; the negative correlation mapping result of the heating sufficiency of each neighborhood window is positively fused with the skin effect severity to obtain the induction heating sufficiency of each neighborhood window.

[0009] Based on the environmental medium interference and the induction heating sufficiency of each neighborhood window, obtain the heating control factor of each neighborhood window; based on the numerical value of the heating control factor of all neighborhood windows in each frame of infrared thermal imaging image, control the heating of the induction furnace.

[0010] The dark spot pixels are obtained by:

[0011] Based on the gray value of all pixels in each neighborhood window, the gray scale segmentation threshold is obtained, and the pixels with a gray value greater than the gray scale segmentation threshold are taken as dark spot pixels.

[0012] The granular noise condition of each neighborhood window is obtained by:

[0013] The difference between the mean value of the gray value of all non-dark spot pixels and the mean value of the gray value of all dark spot pixels in each neighborhood window is obtained, which is denoted as the gray difference; the confusion degree of the two-dimensional coordinates of all dark spot pixels in each neighborhood window is obtained; the result of positively fusing the gray difference and the confusion degree is taken as the granular noise condition of each neighborhood window.

[0014] The edge gradient blur condition of each neighborhood window is obtained by:

[0015] The mean value of the gray gradient of all edge pixels in each neighborhood window is calculated, and the dispersion degree of the gray gradient direction angle of all edge pixels in each neighborhood window is obtained; the result of positively fusing the mean value of the gray gradient and the dispersion degree of each neighborhood window is taken as the edge gradient blur condition of each neighborhood window.

[0016] The skin effect severity of each neighborhood window is obtained by:

[0017] Taking each edge pixel in the neighborhood window as the starting point, any edge pixel in the neighborhood window and all pixels with a vertical coordinate less than the vertical coordinate of each edge pixel are obtained, and the sequence of gray values of all pixels obtained by the any edge pixel is denoted as the skin depth sequence of the any edge pixel.

[0018] The product of the range value and the coefficient of variation of the sequence of the skin depth corresponding to each edge pixel in each neighborhood window is calculated, all the products obtained by each neighborhood window are accumulated, and the skin effect severity of each neighborhood window is obtained.

[0019] The specific process of obtaining the heating sufficiency degree of each neighborhood window is as follows:

[0020] The average value of the gray values of all pixels in each neighborhood window in each frame of the infrared thermal imaging image is calculated, and the sequence of the average value of the gray values of each neighborhood window in the current frame and in all previous frames of the infrared thermal imaging image of the induction furnace is recorded as the gray average value sequence of each neighborhood window in the current frame.

[0021] The similarity between each neighborhood window and the gray average value sequence of the remaining neighborhood windows in the current frame is obtained, all the similarities obtained by each neighborhood window are accumulated, and the average value of the gray values of all pixels in each neighborhood window is multiplied to obtain the heating sufficiency degree of each neighborhood window.

[0022] The heating control factor of each neighborhood window is obtained, which is the reciprocal of the product of the environmental medium interference and the induction heating sufficiency, and the result is normalized.

[0023] The process of controlling the heating of the induction furnace includes:

[0024] The average value of the heating control factors of all neighborhood windows in the infrared thermal imaging image is calculated, and when the obtained average value is less than the preset heating control threshold, it is determined that the temperature of the induction furnace does not need to be adjusted; otherwise, the temperature of the induction furnace is increased by a preset temperature amplitude.

[0025] According to another aspect of the present application, an induction furnace heating control device is provided, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the method according to any one of the above aspects when executing the computer program.

[0026] According to still another aspect of the present application, an induction furnace heating control system is provided, and the system stores a computer program, which is executed by a processor to implement the method according to any one of the above aspects.

[0027] The present application has at least the following beneficial effects:

[0028] The application is directed to the technical defects that the induction furnace environment medium interference and the skin effect caused by the alternating electromagnetic field of the induction coil cannot accurately identify the material induction heating sufficient condition in the process of capturing the global temperature field of the material induction heating by infrared thermal imaging technology for controlling the temperature of the induction coil of the induction furnace. A calculation and quantization method of environmental medium interference and induction heating sufficiency is provided, and the environmental medium interference condition of the infrared thermal imaging image of the material in the induction furnace, the severity of the skin effect of the material and the heating sufficiency of the material are more accurately evaluated.

[0029] Further, the overall heating condition of the material in the induction furnace is evaluated by the heating control factor, and the temperature of the induction coil of the induction furnace is adjusted based thereon. The degree of environmental noise interference and the temperature field uniformity of the material induction heating are comprehensively considered, the disadvantages of false adjustment caused by environmental interference and material skin effect when the infrared thermal imaging technology is used to evaluate the induction coil temperature control of the induction furnace are effectively avoided, the induction coil temperature of the induction furnace can be accurately adjusted on the basis of accurately evaluating the induction heating sufficiency and uniformity of the material, and the energy transmission efficiency, automatic control precision and energy consumption of the induction furnace are improved. BRIEF DESCRIPTION OF DRAWINGS

[0030] Figure 1 A step flow chart of an induction furnace heating control method provided by the application is provided.

[0031] Figure 2 A heating control factor acquisition flowchart provided by the application is provided. DETAILED DESCRIPTION

[0032] In the description of the embodiments of the application, the words "exemplary", "or", "for example" are used to mean as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words "exemplary", "or", "for example" are used to present the relevant concept in a specific manner.

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which the application belongs. The terms used in the specification of the application are only for the purpose of describing the specific embodiments and are not intended to limit the application.

[0034] It should be noted that the terms "first", "second" in the present application and the drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The method disclosed in the embodiments of the present application or the method shown in the flowchart includes one or more steps for implementing the method, and the execution order of the steps can be interchanged with each other without departing from the scope of the present application, and some steps can also be deleted.

[0035] Referring to Figure 1 which shows a step flowchart of an induction furnace heating control method provided by an embodiment of the present application, the method comprises the following steps:

[0036] Step 1: Obtain infrared thermal imaging images of all frames in the induction furnace heating process.

[0037] In order to avoid the strong magnetic field interference of the induction coil of the induction furnace and ensure the visual angle coverage of the material, the infrared thermal imager is arranged in parallel to the material, and the infrared thermal imaging images of the material in the induction furnace heating process are obtained on the side of the induction furnace. The acquisition frame rate of the infrared thermal imager needs to match the temperature rising rate of the induction furnace to ensure that each frame of image captures the temperature change In the present embodiment, the acquisition frame rate of the infrared thermal imager is set to 20 fps, and the trigger mode is set to continuous triggering, so as to ensure that the infrared thermal imager continuously acquires the infrared thermal imaging images of the material in the induction furnace.

[0038] In order to improve the accuracy of the temperature field identification of the subsequent infrared thermal imaging of the induction furnace, the above obtained infrared thermal imaging images of the induction furnace are taken as input, the gamma transformation algorithm is used to obtain the infrared thermal imaging images of the induction furnace with enhanced contrast, the Lucas-Kanade algorithm is used to detect the feature points in the adjacent image frames, the motion vector of the feature points is calculated, the image coordinates of the current frame are adjusted, the material position is aligned with the previous frame, and the continuity of the induction heating monitoring and control is ensured. Since the gamma transformation algorithm and the Lucas-Kanade algorithm are both known technologies, the specific acquisition process will not be described in detail.

[0039] At this point, the real-time infrared thermal imaging images in the induction furnace heating process can be obtained by the above method.

[0040] Step two: presetting a neighborhood window of the infrared thermal imaging image, segmenting the gray value of each pixel in each neighborhood window to obtain dark spot pixels; analyzing the gray distribution difference between all dark spot pixels and the remaining pixels in each neighborhood window, combining the position distribution of all dark spot pixels to obtain the shot noise condition of each neighborhood window; analyzing the distribution of the gray gradient and the distribution of the gray gradient direction angle of the edge pixels in each neighborhood window to obtain the edge gradient blur condition of each neighborhood window; obtaining the environmental medium interference of each neighborhood window based on the shot noise condition and the edge gradient blur condition of each neighborhood window.

[0041] In the induction furnace heating process, the moisture contained in the material will gradually release water vapor during the heating process, and the material may decompose or volatilize during the high-temperature heating process of the induction furnace, releasing solid particles suspended in the induction furnace to form dust. The scattering effect of dust in the induction furnace on infrared light will increase with the increase of particle concentration, and water vapor will strongly absorb infrared radiation, which will cause distortion and interference of the contrast and temperature distribution of the induction furnace material heating infrared thermal imaging image, and the temperature field formed by the induction coil cannot be accurately distinguished.

[0042] Specifically, in the induction furnace heating process, when the infrared thermal imaging image is more seriously interfered by the environmental medium, the shot noise phenomenon is significant in the local range of the induction furnace infrared thermal imaging image affected by the scattering effect of infrared radiation, that is, the random distribution of dark spot regions in the local range of the infrared thermal imaging image is obvious, and the gray value of the dark spot region is affected by the scattering or absorption effect of the environmental medium, so that the difference between the gray value and the gray value in the local range is large; at the same time, the main scattering effect of the environmental medium in the vertical direction makes the edge gradient intensity of the material in the infrared thermal imaging image more blurred, and the edge gradient change trend is more random.

[0043] Based on the above analysis, the present application takes any one frame of induction furnace infrared thermal imaging image as an example for subsequent processing, constructs the environmental medium interference, which is used to represent the shot noise serious condition and the edge gradient blur degree caused by the interference of the environmental medium in the induction furnace in the neighborhood range. The present application divides the infrared thermal imaging image into N neighborhood windows of the same size, and the size of the neighborhood window is 7 7, and the neighborhood window less than 7 7 is processed by linear interpolation. The size of the neighborhood window can also be set by the implementer according to the actual situation; the gray value of all pixels in each neighborhood window in the induction furnace infrared thermal imaging image is taken as the input, and the OTSU threshold segmentation is used to obtain the gray threshold of each neighborhood window. Each neighborhood window is recorded as the dark spot pixel of each neighborhood window, and the position coordinates are obtained.

[0044] The edge detection algorithm based on Canny operator is used to obtain all edge pixels in the infrared thermal imaging image of the induction furnace, and the gray gradient direction angle and the gray gradient value in the vertical direction of all edge pixels in each neighborhood window are obtained by using the sobel operator.

[0045] The difference between the average of the gray values of all non-dark spot pixels and the average of the gray values of all dark spot pixels in each neighborhood window is obtained, denoted as the gray difference; the confusion degree of the two-dimensional coordinates of all dark spot pixels in each neighborhood window is obtained; the result of the forward fusion of the gray difference and the confusion degree is taken as the shot noise condition of each neighborhood window; the difference between variables in this embodiment is calculated by difference, and the gray difference is denoted as a; the confusion degree between multiple variables in this embodiment is calculated by information entropy, and the confusion degree is denoted as b; the shot noise condition of each neighborhood window is denoted as , and the formula is ; in the formula, represents a natural constant.

[0046] The average of the gray gradients of all edge pixels in each neighborhood window is calculated, and the dispersion degree of the gray gradient direction angle of all edge pixels in each neighborhood window is obtained; the result of the forward fusion of the average of the gray gradients and the dispersion degree of each neighborhood window is taken as the edge gradient blur condition of each neighborhood window. In this embodiment, the dispersion degree between multiple variables is calculated by variance, and it should be noted that if the neighborhood window does not contain edge pixels or contains only one edge pixel, the edge gradient blur condition of the neighborhood window is set to 1; the edge gradient blur condition of each neighborhood window is denoted as , and the formula is ; in the formula, c represents the average of the gray gradients of all edge pixels in each neighborhood window; d represents the variance of the gray gradient direction angle of all edge pixels in each neighborhood window.

[0047] Further, the product of the shot noise condition and the edge gradient blur condition of each neighborhood window is normalized to obtain the environmental medium interference of each neighborhood window. In this embodiment, the normalization function adopts a sigmoid function, and the implementer can determine the normalization function according to the actual situation.

[0048] It should be understood that the environmental medium interference is used to reflect the difference in granular noise gray distribution caused by the environmental medium interference in each neighborhood window range of the induction furnace infrared thermal imaging image and the abnormal condition of the edge gradient intensity; the granular noise condition is used to reflect the difference in dark spot pixel gray and the distribution dispersion condition of the dark spot pixel in each neighborhood window range of the induction furnace infrared thermal imaging image; and the edge gradient blur condition is used to represent the blur degree of the vertical direction edge gradient intensity caused by the scattering effect of the environmental medium in the induction furnace infrared thermal imaging image and the randomness of the edge gradient direction. During the induction furnace heating process, the more serious the interference of the environmental medium in the induction furnace on the infrared thermal imaging image of the material, the more dispersed the dark spot distribution caused by the scattering effect of infrared radiation in the infrared thermal imaging image, and the smaller the corresponding gray value of the dark spot area, that is, the larger the granular noise condition; at the same time, due to the main scattering effect of the environmental medium in the vertical direction, the smaller the gray gradient value of the material edge in the vertical direction in the neighborhood window, and the stronger the difference in the gradient direction of the material edge pixel, that is, the larger the edge gradient blur condition.

[0049] At this point, the environmental medium interference of each neighborhood window in any frame of infrared thermal imaging image during the induction furnace heating process can be obtained by the above-mentioned manner.

[0050] Step three: analyze the distribution characteristics of the gray value of each edge pixel in the vertical direction in each neighborhood window to obtain the skin effect severity condition of each neighborhood window; based on the similarity degree of the gray distribution of each neighborhood window and the remaining neighborhood windows in the current frame and all previous frames of infrared thermal imaging image, obtain the heating sufficiency degree of each neighborhood window; and positively fuse the negative correlation mapping result of the heating sufficiency degree of each neighborhood window with the skin effect severity condition to obtain the induction heating sufficiency of each neighborhood window.

[0051] In the induction furnace heating control process, the alternating electromagnetic field of the induction coil will cause the induction heating of the material to produce skin effect, and the eddy current density of the material surface is higher than that of the inside, which causes the material surface temperature to rise faster and the actual temperature of the material inside to be lower, which affects the identification of the temperature field in the infrared thermal imaging image; relying only on the interference of the environmental medium to control the induction furnace heating is insufficient, because it lacks quantitative analysis of the induction heating state of the material in the furnace, and cannot accurately evaluate the actual situation of the material heating. This way may cause the heating control strategy to be executed incorrectly, thereby affecting the heating quality of the material.

[0052] Specifically, in the induction furnace heating process, when the material is subjected to the skin effect generated by the alternating electromagnetic field of the induction coil, the lighter the skin effect and the higher the degree of induction heating of the material, the greater the skin depth of the material edge in the vertical direction in the infrared thermal imaging image of the induction furnace, that is, the smaller the extreme difference in gray value between the material edge pixel and the pixel in the vertical direction, and the more uniform the gray value change of the material edge pixel in the vertical direction; at the same time, the material is fully affected by induction heating, so that the high gray value condition in the infrared thermal imaging image is more obvious, and the difference between the gray value change trends in different neighborhood ranges in the material infrared thermal imaging image gradually decreases over time.

[0053] Based on the above analysis, the induction heating sufficiency is constructed to represent the skin effect severity of the material in each neighborhood window in the infrared thermal imaging image of the induction furnace and the degree of induction heating of the material. Taking any neighborhood window in the infrared thermal imaging image of the induction furnace as an example for subsequent processing, taking each edge pixel in the neighborhood window as the starting point, obtaining any edge pixel in the neighborhood window and all pixels with a vertical coordinate less than the vertical coordinate of each edge pixel, and the sequence of gray values of all pixels obtained by the any edge pixel is referred to as the skin depth sequence of the any edge pixel.

[0054] The average gray value of all pixels in each neighborhood window in each frame of the infrared thermal imaging image of the induction furnace is calculated, and the sequence of the average gray values of each neighborhood window in the current frame and in all previous frames of the infrared thermal imaging image of the induction furnace is referred to as the gray value sequence of each neighborhood window in the current frame.

[0055] The similarity between each neighborhood window and the gray value sequence of the remaining neighborhood windows in the current frame is obtained, all the similarities obtained by each neighborhood window are added, and multiplied by the average gray value of all pixels in each neighborhood window to obtain the heating sufficiency of each neighborhood window, which is denoted as In this embodiment, the similarity between the sequences is measured by cosine similarity.

[0056] The product of the element range value and the coefficient of variation of the skin depth sequence corresponding to each edge pixel in each neighborhood window is calculated, and all the products obtained by each neighborhood window are added to obtain the skin effect severity of each neighborhood window, which is denoted as .

[0057] The negative correlation mapping result of the heating sufficiency of each neighborhood window is positively fused with the skin effect severity to obtain the induction heating sufficiency of each neighborhood window, which is denoted as In this embodiment, the formula of the induction heating sufficiency is: .

[0058] It should be understood that the induction heating sufficiency is used to reflect the skin effect severity caused by the alternating electromagnetic field of the induction coil in each neighborhood window range in the infrared thermal imaging image of the induction furnace and the uniformity of the induction heating of the material; the skin effect severity is used to reflect the obviousness of the skin depth of the material in each neighborhood window range in the infrared thermal imaging image of the induction furnace; and the heating sufficiency is used to represent the high temperature degree in each neighborhood window range in the infrared thermal imaging image of the induction furnace and the difference of the temperature change in different neighborhood window ranges. In the induction furnace heating process, when the skin effect caused by the alternating electromagnetic field of the induction coil in the infrared thermal imaging image of the material in the induction furnace is lighter, and the induction heating of the material is more sufficient, the skin depth of the material in each region range in the infrared thermal imaging image is greater, the pixel gray difference value of the material edge pixel in the vertical direction is smaller, the pixel gray value change of the material edge pixel in the vertical direction is more uniform, that is, the skin effect severity is smaller; at the same time, the heating condition in each region in the infrared thermal imaging image of the induction furnace is better, the gray mean value in the neighborhood window is higher, and the difference of the temperature change trend in different neighborhood ranges is smaller over time, that is, the heating sufficiency is greater.

[0059] At this point, the induction heating sufficiency of each neighborhood window in any frame of infrared thermal imaging image of the induction furnace in the induction furnace heating process can be obtained by the above-mentioned manner.

[0060] Step four: based on the environmental medium interference and the induction heating sufficiency of each neighborhood window, the heating control factor of each neighborhood window is obtained; based on the numerical value of the heating control factor of all neighborhood windows in each frame of infrared thermal imaging image, the heating of the induction furnace is controlled.

[0061] In the induction furnace heating control, when the skin effect of the material in the local range in the infrared thermal imaging of the induction furnace caused by the alternating electromagnetic field of the induction coil is lighter, the induction heating of the material is more sufficient and the influence of the environmental medium interference in the induction furnace is more blurred, the heating condition of the material in the induction furnace is more uniform and sufficient, at this time, the temperature of the induction coil of the induction furnace does not need to be adjusted, thereby avoiding excessive heating of the material and waste of energy consumption.

[0062] Therefore, the heating control factor is constructed in the application, which is used to represent the temperature control degree of the induction coil in the induction furnace heating process, which can be obtained by the environmental medium interference and the induction heating sufficiency. Specifically, in one processing condition of the application, the reciprocal of the product of the environmental medium interference and the induction heating sufficiency of each neighborhood window in the infrared thermal imaging image of the induction furnace is obtained, and the result obtained by normalization is used as the heating control factor of each neighborhood window, and the normalization function adopts the sigmoid function in the embodiment.

[0063] The acquisition process of the heating control factor is shown in the schematic diagram of Figure 2 .

[0064] In the induction furnace heating control process, when the induction heating sufficiency in the neighborhood window is lower and the environmental medium interference is also lower, it indicates that the material induction furnace infrared thermal imaging image quality is less disturbed by the environmental medium interference, and the material temperature field characteristics can be accurately characterized. At this time, the heating condition of the material in the induction furnace is more uneven and sufficient, the skin effect phenomenon caused by the alternating electromagnetic field of the induction coil is more serious, and the induction coil temperature of the induction furnace should be timely increased to ensure the sufficient and uniform heating of the material and improve the energy transfer efficiency of the induction furnace.

[0065] At this point, the heating control factor of each neighborhood window in any frame of induction furnace infrared thermal imaging image in the induction furnace heating process can be obtained by the above-mentioned manner.

[0066] The application sets a heating control threshold P. In order to prevent the insufficient control precision of the induction furnace coil temperature due to the short induction furnace infrared thermal imaging image acquisition time, the induction furnace coil temperature cold start control period is set to 2 min, that is, the first time after 2 min of the induction furnace heating control is taken as the earliest time of each induction furnace coil temperature control.

[0067] When the average of the heating control factors corresponding to all neighborhood windows in the induction furnace infrared thermal imaging image is less than the heating control threshold, it is considered that the heating sufficiency of the material in the current induction furnace is uniform and good, and the skin effect phenomenon caused by the alternating electromagnetic field of the induction coil is slight, and the induction coil temperature of the induction furnace does not need to be adjusted. On the contrary, when the average of the heating control factors corresponding to all neighborhood windows in the induction furnace infrared thermal imaging image is greater than or equal to the heating control threshold, it is considered that the induction heating condition of the material in the current induction furnace is uneven, the heating degree is insufficient, and the skin effect phenomenon caused by the alternating electromagnetic field of the induction coil is serious. At this time, the induction coil temperature of the induction furnace should be increased to ensure the sufficient and uniform induction heating of the material. In the application, the heating control threshold P and the induction coil temperature of the induction furnace are respectively 0.6 and 10℃. In the embodiment, the temperature of the induction coil of the induction furnace can be realized by adjusting the output power of the induction furnace power supply through the PLC programmable logic controller. Since the PLC adjustment control of the output power of the induction furnace power supply is a known technology, the specific acquisition process will not be described in detail, and the implementer can set the heating control threshold P and the induction coil temperature of the induction furnace according to the actual situation.

[0068] Based on the same concept as the method embodiment of the application, an induction furnace heating control device is provided, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned any one method are realized.

[0069] Based on the same concept as the method embodiments of the present application, an induction furnace heating control system is provided, wherein a computer program is stored in the system, and the computer program is executed by a processor to implement any of the above methods.

[0070] It should be noted that the flowcharts and block diagrams in the accompanying drawings show the architectural, functional and operational logic of possible implementations of the systems, methods and computer program products according to the embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, a program segment or a portion of code that contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks can occur in different orders than those noted in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks can also occur in different orders than those disclosed in the descriptions, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. Each block in the block diagrams and / or flowcharts, and the combination of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0071] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. An induction furnace heating control method characterized by, The method comprises the following steps: Obtaining infrared thermal imaging images of all frames in the induction furnace heating process; Predefining a neighborhood window of the infrared thermal imaging image, segmenting the gray value of each pixel in each neighborhood window to obtain dark spot pixels, analyzing the gray distribution difference between all dark spot pixels and the remaining pixels in each neighborhood window, combining the position distribution of all dark spot pixels to obtain the shot noise condition of each neighborhood window, analyzing the distribution of the gray gradient of the edge pixels in each neighborhood window and the distribution of the gray gradient direction angle to obtain the edge gradient blur condition of each neighborhood window, and forwardly fusing the shot noise condition and the edge gradient blur condition of each neighborhood window to obtain the environmental medium interference of each neighborhood window; Analyzing the distribution characteristics of the gray value of the pixels in the vertical direction of each edge pixel in each neighborhood window to obtain the skin effect severity condition of each neighborhood window, and obtaining the heating sufficiency of each neighborhood window based on the similarity of the gray distribution of each neighborhood window and the remaining neighborhood windows in the current frame and all previous frames of infrared thermal imaging images. Based on the environmental medium interference and the induction heating sufficiency of each neighborhood window, a heating control factor of each neighborhood window is obtained, and the heating of the induction furnace is controlled based on the numerical value of the heating control factor of all neighborhood windows in each frame of infrared thermal imaging image.

2. The induction furnace heating control method of claim 1, wherein, The dark spot pixels are obtained by segmenting the gray value of all pixels in each neighborhood window to obtain a gray segmentation threshold, and the pixels with a gray value greater than the gray segmentation threshold are taken as dark spot pixels. The shot noise condition of each neighborhood window comprises:

3. The induction furnace heating control method of claim 1, wherein, Obtaining the difference between the mean value of the gray value of all non-dark spot pixels and the mean value of the gray value of all dark spot pixels in each neighborhood window, denoted as the gray difference, obtaining the confusion degree of the two-dimensional coordinates of all dark spot pixels in each neighborhood window, and forwardly fusing the gray difference and the confusion degree to obtain the shot noise condition of each neighborhood window. The edge gradient blur condition of each neighborhood window is obtained by calculating the mean value of the gray gradient of all edge pixels in each neighborhood window and obtaining the dispersion degree of the gray gradient direction angle of all edge pixels in each neighborhood window, and forwardly fusing the mean value of the gray gradient and the dispersion degree of each neighborhood window to obtain the edge gradient blur condition of each neighborhood window.

4. The induction furnace heating control method of claim 1, wherein, The skin effect severity condition of each neighborhood window is obtained by taking each edge pixel in the neighborhood window as a starting point, obtaining any edge pixel and all pixels in the vertical direction with a longitudinal coordinate less than that of each edge pixel within the range of the neighborhood window, and taking the sequence of the gray values of all pixels obtained by the any edge pixel as the skin depth sequence of the any edge pixel. ​ 5. The method of claim 1, wherein the step of determining the power level of the induction furnace comprises the steps of: determining the power level of the induction furnace based on the sensed temperature of the induction furnace and the sensed temperature of the workpiece. ​ ​ The product of the range value and the coefficient of variation of the elements of the skin depth sequence corresponding to each edge pixel in each neighborhood window is calculated, and all the products obtained by each neighborhood window are accumulated to obtain the skin effect severity of each neighborhood window.

6. The method of claim 1, wherein the step of determining the power level of the induction furnace comprises the steps of: determining a power level of the induction furnace; and determining a power level of the induction furnace based on the determined power level of the induction furnace. The specific process of obtaining the heating sufficiency degree of each neighborhood window is as follows: The mean value of the gray values of all pixels in each neighborhood window in each frame of the infrared thermal imaging image is calculated, and a sequence composed of the mean values of the gray values of all pixels in each neighborhood window in the current frame and in all previous frames of the infrared thermal imaging image of the induction furnace is recorded as the gray mean value sequence of each neighborhood window in the current frame. The similarity between each neighborhood window and the gray mean value sequence of the remaining neighborhood windows in the current frame is obtained, all the similarities obtained by each neighborhood window are accumulated, and the mean value of the gray values of all pixels in each neighborhood window is multiplied to obtain the heating sufficiency degree of each neighborhood window.

7. The induction furnace heating control method as described in claim 1, characterized in that, The heating control factor of each neighborhood window is obtained, which is the reciprocal of the product of the environmental medium interference and the induction heating sufficiency, and the result is normalized.

8. The induction furnace heating control method as described in claim 1, characterized in that, The process of controlling the heating of the induction furnace includes: The mean value of the heating control factors of all neighborhood windows in the infrared thermal imaging image is calculated, and if the obtained mean value is less than a preset heating control threshold, it is determined that the temperature of the induction furnace does not need to be adjusted; otherwise, the temperature of the induction furnace is increased by a preset temperature amplitude.

9. An induction stove heating control apparatus comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, The processor executes the computer program to realize the steps of the method of any one of claims 1-8.

10. An induction furnace heating control system, in which a computer program is stored, characterized in that, The computer program is executed by the processor to realize the method of any one of claims 1-8.

Images